Department of Electrical and Electronics Engineering, Rajiv Gandhi Institute of Technology, Kottayam, India.
APJ Abdul Kalam Technological University, Thiruvananthapuram, India.
Phys Eng Sci Med. 2022 Jun;45(2):623-635. doi: 10.1007/s13246-022-01129-z. Epub 2022 May 19.
Diabetic retinopathy (DR) is a progressive vascular complication that affects people who have diabetes. This retinal abnormality can cause irreversible vision loss or permanent blindness; therefore, it is crucial to undergo frequent eye screening for early recognition and treatment. This paper proposes a feature extraction algorithm using discriminative multi-sized patches, based on deep learning convolutional neural network (CNN) for DR grading. This comprehensive algorithm extracts local and global features for efficient decision-making. Each input image is divided into small-sized patches to extract local-level features and then split into clusters or subsets. Hierarchical clustering by Siamese network with pre-trained CNN is proposed in this paper to select clusters with more discriminative patches. The fine-tuned Xception model of CNN is used to extract the global-level features of larger image patches. Local and global features are combined to improve the overall image-wise classification accuracy. The final support vector machine classifier exhibits 96% of classification accuracy with tenfold cross-validation in classifying DR images.
糖尿病视网膜病变（DR）是一种影响糖尿病患者的进行性血管并发症。这种视网膜异常可导致不可逆转的视力丧失或永久性失明；因此，进行频繁的眼部筛查以早期发现和治疗至关重要。本文提出了一种基于深度学习卷积神经网络（CNN）的判别多尺寸斑块特征提取算法，用于 DR 分级。该综合算法提取局部和全局特征，以实现高效决策。每个输入图像被分为小尺寸斑块以提取局部特征，然后将其划分为簇或子集。本文提出了一种基于孪生网络的分层聚类方法，以选择具有更多判别性斑块的簇。使用经过预训练的 CNN 的微调 Xception 模型提取较大图像斑块的全局特征。局部和全局特征相结合，提高了整体图像分类精度。最终的支持向量机分类器在十折交叉验证中对 DR 图像的分类准确率达到 96%。
